中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

39 records (took 0.025 seconds)

    LOCALIZATION METHOD AND APPARATUS BASED ON 3D COLOR MAP
    12.
    发明申请
    LOCALIZATION METHOD AND APPARATUS BASED ON 3D COLOR MAP 审中-公开

    公开(公告)号：US20200184727A1

    公开(公告)日：2020-06-11

    申请号：US16508513

    申请日：2019-07-11

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Inwoo HA ,  Nahyup KANG

    IPC: G06T19/00 ,  G06T7/73 ,  G06T15/10

    Abstract: A localization method and apparatus are provided. The method comprises generating a synthetic image corresponding to a current time period based on a three-dimensional (3D) color map corresponding to an image captured at a time period prior to the current time period, and position information at the current time period time, and determining final position information at the current time period based on the synthetic image corresponding to the current time period and an image captured at the current time period.

    IMAGE PROCESSING APPARATUS AND METHOD
    13.
    发明申请
    IMAGE PROCESSING APPARATUS AND METHOD 有权
    图像处理装置和方法

    公开(公告)号：US20160171754A1

    公开(公告)日：2016-06-16

    申请号：US14945753

    申请日：2015-11-19

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Minsu AHN ,  Seungin PARK ,  Inwoo HA ,  Hyong Euk LEE

    IPC: G06T15/50 ,  G06T15/80

    CPC classification number: G06T15/506 ,  G06T15/50 ,  G06T15/55 ,  G06T15/80

    Abstract: An image processing apparatus includes a calculator configured to calculate a first difference value between frames in terms of either one or both of a position and a direction of a direct light by comparing a current frame to at least one previous frame, and a determiner configured to determine that an indirect light of the current frame is to be sampled in response to the first difference value being greater than or equal to a threshold.

    Abstract translation: 一种图像处理装置包括：计算器，被配置为通过将当前帧与至少一个先前帧进行比较来计算在直接光的位置和方向中的任一个或两个方面的帧之间的第一差值;以及确定器，被配置为 确定响应于第一差值大于或等于阈值来对当前帧的间接光进行采样。

    METHOD AND APPARATUS WITH IMAGE PROCESSING AND RECONSTRUCTED IMAGE GENERATION
    14.
    发明申请
    METHOD AND APPARATUS WITH IMAGE PROCESSING AND RECONSTRUCTED IMAGE GENERATION 有权

    公开(公告)号：US20220284663A1

    公开(公告)日：2022-09-08

    申请号：US17487240

    申请日：2021-09-28

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Inwoo HA ,  Hyun Sung CHANG ,  Minjung SON

    IPC: G06T15/50 ,  G06T7/50 ,  G06T15/80

    Abstract: A processor-implemented method includes: determining albedo data in a canonical space and depth data in the canonical space based on input image data including an object, using one or more neural network-based extraction models; generating deformed albedo data and deformed depth data by applying a target shape deformation value respectively to the albedo data and the depth data; generating resultant shaded data by performing shading based on the deformed depth data and a target illumination value; generating intermediate image data based on the resultant shaded data and the deformed albedo data; and generating reconstructed image data from the intermediate image data and the deformed depth data based on a target pose value.

    METHOD AND APPARATUS WITH IMAGE SEGMENTATION
    15.
    发明申请
    METHOD AND APPARATUS WITH IMAGE SEGMENTATION 审中-公开

    公开(公告)号：US20190295261A1

    公开(公告)日：2019-09-26

    申请号：US16103187

    申请日：2018-08-14

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Nahyup KANG ,  KeeChang LEE ,  Inwoo HA

    IPC: G06T7/136 ,  G06N3/08 ,  G06N3/04 ,  G06K9/62

    Abstract: A processor-implemented learning method for an image segmentation includes training first duplicate layers, as duplications of trained first layers of a pre-trained model, so that a second feature extracted from a target image by the trained first duplicate layers is matched to a first feature extracted from a training image by the trained first layers; regularizing the trained first duplicate layers so that a similarity between the first feature and a third feature extracted from the training image by the regularized first duplicate layers meets a threshold; and training second duplicate layers, as duplications of trained second layers of the pre-trained model, to be configured to segment the target image based on the regularized first duplicate layers, the trained second layer being configured to segment the training image.

    IMAGE PROCESSING APPARATUS AND METHOD
    20.
    发明申请
    IMAGE PROCESSING APPARATUS AND METHOD 审中-公开
    图像处理装置和方法

    公开(公告)号：US20160148420A1

    公开(公告)日：2016-05-26

    申请号：US14945694

    申请日：2015-11-19

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Inwoo HA ,  Seungin PARK ,  Minsu AHN ,  Hyong Euk LEE

    IPC: G06T15/80

    CPC classification number: G06T15/80 ,  G06T15/005 ,  G06T15/50

    Abstract: An image processing apparatus includes a first shader configured to perform a light shading operation associated with at least one light source on a three-dimensional (3D) model at a first resolution to obtain a light shading result of the first resolution; a second shader configured to perform a surface shading operation on the 3D model at a second resolution different from the first resolution to obtain a surface shading result of the second resolution; and a processor configured to generate a rendering result by combining the light shading result of the first resolution with the surface shading result of the second resolution.

    Abstract translation: 一种图像处理装置包括第一着色器，其被配置为以第一分辨率执行与三维（3D）模型上的至少一个光源相关联的遮光操作，以获得第一分辨率的遮光结果; 第二着色器，其被配置为以与所述第一分辨率不同的第二分辨率对所述3D模型执行表面着色操作，以获得所述第二分辨率的表面阴影结果; 以及处理器，被配置为通过将所述第一分辨率的所述遮光结果与所述第二分辨率的表面阴影结果组合来生成呈现结果。

Patent Agency Ranking